论文标题
零阶随机坐标方法分散的非凸优化
Zeroth-Order Stochastic Coordinate Methods for Decentralized Non-convex Optimization
论文作者
论文摘要
在这封信中，我们首先提出A \下划线{z} eroth- \下划线{o} rder c \ c \下划线{o}坐标\下划线\下划线{m} Ethod〜（Zoom）在仅使用Zeroth-Order-Order-oracle〜（ZO）Oracle Backback可获得的分散网络上解决随机优化问题。此外，我们配备了一种简单的机制“强力球”，以变焦并提出Zoom-PB，以加速变焦的融合。与现有方法相比，我们通过文献中的两个基准示例验证了所提出的算法，即黑盒二进制分类和来自黑盒DNN的生成对抗性示例，以便与现有的最先进的集中和分布式的ZO算法进行比较。数值结果表明，所提出的算法的收敛速率更快。
In this letter, we first propose a \underline{Z}eroth-\underline{O}rder c\underline{O}ordinate \underline{M}ethod~(ZOOM) to solve the stochastic optimization problem over a decentralized network with only zeroth-order~(ZO) oracle feedback available. Moreover, we equip a simple mechanism "powerball" to ZOOM and propose ZOOM-PB to accelerate the convergence of ZOOM. Compared with the existing methods, we verify the proposed algorithms through two benchmark examples in the literature, namely the black-box binary classification and the generating adversarial examples from black-box DNNs in order to compare with the existing state-of-the-art centralized and distributed ZO algorithms. The numerical results demonstrate a faster convergence rate of the proposed algorithms.
